Rob Wiederstein
33d0fc31c7
End-to-end LightGBM fraud detection pipeline built as an R package, orchestrated by targets with data stored in MinIO via Apache Arrow. Includes 6-layer Lakehouse architecture, class imbalance tournament, formally tuned hyperparameters (PR-AUC 0.198), and Quarto RevealJS slides. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
28 lines
839 B
R
28 lines
839 B
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/functions.R
|
|
\name{evaluate_final_model}
|
|
\alias{evaluate_final_model}
|
|
\title{Final Model Evaluation (Months 6 & 7)}
|
|
\usage{
|
|
evaluate_final_model(
|
|
params,
|
|
bucket_name = "baf-fraud",
|
|
inputs_prefix = "05_model_input"
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{params}{A named list of LightGBM hyperparameters with elements:
|
|
\code{trees}, \code{tree_depth}, \code{learn_rate}, \code{loss_reduction}, \code{min_n}.}
|
|
|
|
\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
|
|
|
|
\item{inputs_prefix}{Character. Model input prefix. Default "05_model_input".}
|
|
}
|
|
\value{
|
|
A tibble with columns \code{truth}, \code{prob}, and \code{pred_class}.
|
|
}
|
|
\description{
|
|
Trains the winning strategy on the full training set (Months 0-5)
|
|
and evaluates it on the unseen test set (Months 6-7).
|
|
}
|